Atlanta, GA, USA
March 29, 2015


March 29,2015
9:00am Welcome
9:20am Invited Talk Jean-Claude Martin (LIMSI-CNRS / University Paris South) "Affective Multimodal Interaction"
10:00am Coffee Break
10:30am Paper Session I (each 15 min presentation + 9 min discussion)
  • AmbLEDs: Implicit I/O for AAL Systems
  • Personalized interactive public screens
  • Mining users' online communication for improved interaction with context-aware systems
  • Modality Selection Based on Agent Negotiation for Voice Search on Smartphones Paired With Wearable Accessories: A Preliminary Architectural Design
  • In-air Eyes-free Text Entry
12:30pm Lunch Break
1:30pm Poster & Demo Session
2:00pm Selection of topics to discuss
2:10pm In-depth discussion on selected topics I
3:00pm Coffee Break
3:30pm In-depth discussion on selected topics II
3:50pm Workshop Summary
4:00pm Workshop End

Invited Talk

Jean-Claude Martin - Affective Multimodal Interaction
There is an increasing interest in several disciplines and domains about the processing of affects in intelligent user interfaces. In my talk, I will first summarize the main underlying concepts and then illustrate them with different studies that we conducted in my pluridisciplinary group. These studies tackle the theories and models of emotions and personality but also the recognition and the expression of affects in several non-verbal modalities such as haptics, facial expressions and body movements.


List of Accepted Papers

Paper Session I

Marcio Cunha, Hugo Fuks: AmbLEDs: Implicit I/O for AAL Systems
PDF Ambient Assisted Living (AAL) applications aim to allow elderly, sick and disabled people to stay safely at home while collaboratively assisted by their family, friends and medical staff. In principle, AAL amalgamated with Internet of Things introduces a new healthcare connectivity paradigm that interconnects mobile apps and sensors allowing constant monitoring of the patient. By hiding technology into light fixtures, in this paper we present AmbLEDs, a ambient light sensing system, as an alternative to spreading sensors that are perceived as invasive, such as cameras, microphones, microcontrollers, tags or wearables, in order to create a crowdware ubiquitous context-aware implicit interface for recognizing, informing and alerting home environmental changes and human activities to support continuous proactive care.

Paolo Cremonesi, Antonella Di Rienzo, Franca Garzotto: Personalized interactive public screens
PDF Crowded public indoor events such as expositions or fairs are nowadays common in large cities; a significant example of such kind of events is Expo 2015 that will take place in Milan during the current year. A lot of people usually crowd these shows and within this context experimental interactive media installations are gaining recognition as new art form. Considering the emerging need to support masses, matching offers to users and personalizing recommendations, there are other interesting possibilities of using the same digital infrastractures for contributing to a lively urban society, improving visitors experience. In order to achieve this, we developed an information service that integrates multiple (touch and touchless) interaction paradigms on personal devices and large public displays. It exploits personalization techniques in order to offer new engaging user experiences involving large amounts of multimedia contents.

Preeti Bhargava, Oliver Brdiczka, Michael Roberts: Mining users' online communication for improved interaction with context-aware systems
PDF With the advent of the internet, online communication media and social networks have become increasingly pervasive and popular among users for interaction and communication. Integrating these online communications with other sources of a user's context can help improve his interaction with context-aware systems as it enables the systems to provide highly personalized content to both users and groups of users. To this end, a user's communication context (such as the people he communicates with often, and the topics he discusses frequently) becomes an important aspect of his context model and new frameworks and methodologies are required for extracting and representing it. In this paper, we present a hybrid framework derived from traditional graph based and object oriented models that employs various Natural Language Processing techniques for extracting and representing users' communication context from their aggregated online communications. We also evaluate our proposed framework and algorithm using the email communication log of a user.

W. L. Yeung: Modality Selection Based on Agent Negotiation for Voice Search on Smartphones Paired With Wearable Accessories: A Preliminary Architectural Design
PDF Intelligent wearable accessories are becoming popular with smartphone users. They bring more modality options and convenience to our interaction with smartphone applications. Real benefits come when applications can adapt intelligently to the new and existing interface options. This paper suggests how such adaptation can be realised in a voice search application using a multi-agent architecture. A preliminary design of the architecture is presented here together with an outline of our future work.

Ali Alavi, Andreas Kunz: In-air Eyes-free Text Entry
PDF In this paper we provide a system for using in-air interaction techniques for eyes-free text entry. We show that complex tasks as text entry can be performed using a mix of simple pinching gestures, which provides the user with a feedback from his or her own sense of touch, compensating for lack of feedback in many touch and in-air interaction techniques.

About the Workshop

The workshop will take place in conjunction with IUI'15, the International Conference on Intelligent User Interfaces, on March 29, 2015 in Atlanta, GA, USA More...